Bemærk
Adgang til denne side kræver godkendelse. Du kan prøve at logge på eller ændre mapper.
Adgang til denne side kræver godkendelse. Du kan prøve at ændre mapper.
Agent skills are task-specific instruction files that AI coding assistants like Claude and GitHub Copilot can load to perform Azure Databricks development tasks. Skills package domain-specific knowledge, best practices, and workflows into a format optimized for AI consumption. To learn how to extend Genie Code in the Azure Databricks workspace, see Extend Genie Code with agent skills.
Skills follow the open Agent Skills standard. Each skill is a Markdown file with front-matter metadata that describes when and how the skill should be used. AI coding assistants automatically discover and load relevant skills based on the task at hand.
Install skills
Install Azure Databricks AI skills using the Databricks CLI aitools command group. The CLI detects supported coding agents and installs Azure Databricks skills so your AI coding assistant can work effectively with Azure Databricks resources such as bundles, jobs, SQL, and more.
# Install Databricks AI skills for all detected agents
databricks aitools install
# Install skills for a specific agent
databricks aitools install --agents claude-code
# Install skills into the current project instead of globally
databricks aitools install --scope project
# Install specific skills
databricks aitools install --skills bundles,sql
Use databricks aitools list, databricks aitools update, and databricks aitools uninstall to manage installed AI tools components. For all options, see aitools command group.
To install skills from arbitrary GitHub repositories that are not distributed through the Databricks CLI, use the Skills CLI, an open-source package manager for agent skills. The Skills CLI scans a GitHub repository for skill files and installs them into your project so that your AI coding assistant can discover and use them automatically.
Skill repositories
| GitHub repository | Description | Skills |
|---|---|---|
| Azure Databricks agent skills | Officially maintained core skills for Azure Databricks development across compute, orchestration, storage, and apps. | Azure Databricks CLI, Databricks Apps, Asset Bundles, Lakeflow Jobs, Lakebase, Model Serving, Lakeflow Spark Declarative Pipelines, serverless migration |
| Databricks app template skills | Task-specific skills embedded inside Databricks app templates for agents (LangGraph, LangChain, OpenAI Agents SDK), App Kits (Lakebase, Genie, Analytics), and chatbot/data app frameworks (Streamlit, Dash, Gradio, Shiny, Flask, Node.js). | Quickstart, deploy, modify-agent, add-tools, create-tools, discover-tools, migrate-from-model-serving, run-locally, load-testing, supervisor APIs |
| AI Dev Kit skills | Curated community skills covering 25+ Azure Databricks development patterns. | Agent Bricks, AI Functions, AI/BI Dashboards, Databricks Apps, Asset Bundles, Databricks Lakehouse, Genie, Iceberg, Lakebase, Lakeflow Jobs, metric views, MLflow evaluation, Model Serving, Python SDK, Lakeflow Spark Declarative Pipelines, Structured Streaming, synthetic data, Unity Catalog, AI Search, Zerobus ingest |
| MLflow skills | Skills for instrumenting, debugging, and evaluating LLM agents with MLflow. | MLflow onboarding, MLflow agent, instrumenting tracing, retrieving and analyzing traces, querying metrics, agent evaluation, chat session analysis, MLflow doc search |
Additional resources
- Extend Genie Code with agent skills: Create skills for the built-in Genie Code in your workspace.
- Migrate an agent from Model Serving to Databricks Apps: Use agent skills to migrate an agent from Model Serving to Databricks Apps.
- Author an AI agent and deploy it on Databricks Apps: Build and deploy an AI agent on Databricks Apps.